Gemini 4 Neon vs Kimi K3.1 Pro
Full profiles: Gemini 4 Neon (Google) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.
Updated · Data from 9 sources
As of 19 Nov 2026, Gemini 4 Neon is ahead of Kimi K3.1 Pro on quality (67.3 vs 60.7 on the BenchLeader Index), but Kimi K3.1 Pro is 1.5× cheaper at $4.00 vs $6.00 per 1M tokens blended. Gemini 4 Neon leads in every category we measure both in. Gemini 4 Neon streams 3×+ faster.
Key facts (as of 19 Nov 2026)
- Gemini 4 Neon scores 67.3 on the BenchLeader Index and Kimi K3.1 Pro scores 60.7 (BenchLeader, 19 Nov 2026).
- Gemini 4 Neon costs $6.00 per 1M tokens blended (list price, 19 Nov 2026).
- Kimi K3.1 Pro costs $4.00 per 1M tokens blended (list price, 19 Nov 2026).
- Gemini 4 Neon streams 3×+ faster than Kimi K3.1 Pro (Artificial Analysis, 7-day median, 19 Nov 2026).
- Of the 13 benchmarks both models have, Gemini 4 Neon leads 10 (BenchLeader, 19 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Gemini 4 Neon | 73 vs 59 category score; FrontierCode 2.0 (AA) 43.3% vs 25.4% | High |
| Agents & tool use | Gemini 4 Neon | 76 vs 60 category score; AutomationBench 79.2% vs 73.3% | High |
| Reasoning | Gemini 4 Neon | 72 vs 58 category score; HLE-Diamond (AA) 68.4% vs 37.3% | High |
| Knowledge | Gemini 4 Neon | 72 vs 57 category score; AA-Omniscience v1.1 53.8 vs 29.9 | High |
| Chat quality (human preference) | – | Only Gemini 4 Neon has an Arena rating (72 category score) | Not comparable |
| Lowest cost | Kimi K3.1 Pro | $4.00 vs $6.00 per 1M blended; agentic coding session $0.160 vs $0.240 | – |
| Fastest first answer | Gemini 4 Neon | 40.6 s (Gemini 4 Neon (high)) vs 155.6 s (Kimi K3.1 Pro) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 4 Neon (high) leads on quality: 67.3 vs 60.7.
- Gemini 4 Neon (high) is stronger in agents & tools, coding, knowledge, reasoning.
- Kimi K3.1 Pro is 1.5× cheaper ($4.00 vs $6.00 per 1M blended).
- Gemini 4 Neon (high) streams 3.3× faster (101 vs 31 tokens per second).
At a glance
| Spec | Gemini 4 Neon | Kimi K3.1 Pro |
|---|---|---|
| Developer | Moonshot AI | |
| Released | 18 Nov 2026 | 23 Oct 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Gemini 4 Neon (high) | Kimi K3.1 Pro |
| Open weights | No | Yes |
| Price in / out / cached input per 1M | $3.00 / $15.00 / $0.150 | $2.00 / $10.00 / $0.200 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Gemini 4 Neon (high) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Reasoning | 71.9 | 57.9 | Gemini 4 Neon |
| Coding | 73.4 | 58.8 | Gemini 4 Neon |
| Agents & tools | 76.2 | 59.5 | Gemini 4 Neon |
| Maths | – | 73.4 | not comparable |
| Knowledge | 72.3 | 57.1 | Gemini 4 Neon |
| Human preference | 71.7 | – | not comparable |
| Multimodal | – | 66.0 | not comparable |
| Long context | – | 67.9 | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Maths, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 13 benchmarks both have, Gemini 4 Neon leads 10, Kimi K3.1 Pro leads 3. Every overall index that rates both puts Gemini 4 Neon ahead.
| Overall index | Gemini 4 Neon (high) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 67.3 | 60.7 | Gemini 4 Neon |
| AA Intelligence Index v5.0.1 | 59.6 | 46.5 | Gemini 4 Neon |
| Arena Text | 1519 | 1487† | Gemini 4 Neon |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Gemini 4 Neon (high) | Kimi K3.1 Pro |
|---|---|---|
| Blended price per 1M tokens | $6.00 | $4.00 |
| Input / output per 1M | $3.00 / $15.00 | $2.00 / $10.00 |
| Cached input per 1M | $0.150 | $0.200 |
| Price per task: chat reply | $0.0057 | $0.0038 |
| Price per task: summarize a 30-page report | $0.045 | $0.030 |
| Price per task: code edit | $0.041 | $0.027 |
| Price per task: agentic coding session | $0.240 | $0.160 |
| Price per task: structured extraction | $0.0090 | $0.0060 |
| Agentic coding session, input mostly cached | $0.112 | $0.079 |
| Cost per benchmark task (AA Index) | $3.74 | $3.68 |
| Output tokens per task (AA Index) | 90k | 72k |
| Of which reasoning | 46k | 44k |
| Time per task (AA Index) | 15 min | 39 min |
| Output speed | 101 tok/s | 31 tok/s |
| Time to first answer | 40.6 s | 155.6 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 417.5 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $3.74 on Gemini 4 Neon (high) and $3.68 on Kimi K3.1 Pro, and Gemini 4 Neon (high) wrote 1.2× as many output tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Neon (high) scores 67.3 and takes 41 s to its first answer token; Gemini 4 Neon (xhigh) scores 64.3 in 57 s. Kimi K3.1 Pro scores 60.7 and takes 156 s to its first answer token; Kimi K3.1 Pro (max) scores 60.2 in 156 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
96 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Gemini 4 Neon (high) | Kimi K3.1 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 67.3 | 60.7 |
| Agents & tools score | BenchLeader | 76.2 | 59.5 |
| Coding score | BenchLeader | 73.4 | 58.8 |
| Human preference score | BenchLeader | 71.7 | – |
| Knowledge score | BenchLeader | 72.3 | 57.1 |
| Reasoning score | BenchLeader | 71.9 | 57.9 |
| Long context score | BenchLeader | – | 67.9 |
| Maths score | BenchLeader | – | 73.4 |
| Multimodal score | BenchLeader | – | 66.0 |
| Blended price $/M | BenchLeader | $6.00 | $4.00 |
| Output speed | BenchLeader | 101 tok/s | 31 tok/s |
| Time to first answer | BenchLeader | 40.6 s | 155.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | 1546 | 1505† |
| LiveBench 2.0 Reasoning | LiveBench | 89.6%† | 91.1%† |
| Humanity's Last Exam (AA) | Artificial Analysis | – | 52.5% |
| HLE-Diamond (AA) | Artificial Analysis | 68.4% | 37.3% |
| CritPt | Artificial Analysis | – | 24.6% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 59.0% | 49.5% |
| MysteryMechanism | Vals AI | – | 26.1%† |
| Arena Expert | Arena (LMArena) | 1541 | 1516† |
| LMCA | Epoch AI Benchmarking Hub | – | 57.6%† |
| DTBench | Epoch AI Benchmarking Hub | – | 93.3%† |
| Coding | |||
| SciCode | SciCode | – | 60.8% |
| Arena Coding | Arena (LMArena) | 1558 | 1537† |
| Arena WebDev | Arena (LMArena) | 1764 | 1685† |
| LiveBench 2.0 Coding | LiveBench | 89.7%† | 67.8%† |
| IOI | Vals AI | – | 81.9%† |
| Vibe Code Bench v1.1 | Vals AI | – | 84.9%† |
| SWE Atlas v1.1 | Scale AI SEAL | – | 61.1% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 70.2% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 58.9% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 54.3% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1932.8† |
| WeirdML v3 | WeirdML | – | 9.9%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 61.6% | 67.2% |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 78.3 |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 84.0† |
Show all 96 benchmarks
| Metric | Publisher | Gemini 4 Neon (high) | Kimi K3.1 Pro |
|---|---|---|---|
| Coding | |||
| Design Arena Website | Design Arena | – | 1318 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 47.1% |
| FrontierCode 2.0 (AA) | Artificial Analysis | 43.3% | 25.4% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 59.7%† |
| APEX-Agents | Mercor | – | 65.5% |
| Arena Agent | Arena (LMArena) | 18.4 | 3.9† |
| LiveBench Long Agentic | LiveBench | 82.6%† | 38.7%† |
| LiveBench Browser | LiveBench | 95.6%† | 75.9%† |
| HiL-Bench | Scale AI SEAL | – | 61.3% |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 67.3% |
| GDPval-AA v2.1 | Artificial Analysis | – | 1861 |
| Analyst Agent (AA) | Artificial Analysis | – | 38.8% |
| Finance Agent v2.1 | Vals AI | – | 61.5%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 11.7%† |
| Legal Research Bench | Vals AI | – | 37.5%† |
| Robo-bench | Vals AI | – | 0.4%† |
| SREBench | Vals AI | – | 27.1%† |
| Tax Agent Bench | Vals AI | – | 24.9%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 63.6%† |
| Terminal-Bench Science | Vals AI | – | 31.4%† |
| Arena Agent Task Completion | Arena (LMArena) | 19.2 | 1.9† |
| AutomationBench | Artificial Analysis | 79.2% | 73.3% |
| GDP.pdf (AA) | Artificial Analysis | 33.4% | 31.4% |
| AA-Briefcase v1.1 | Artificial Analysis | 1632 | 1674 |
| Design Arena Agentic | Design Arena | – | 1291 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 65.7% | 34.3% |
| CWE-Bench (AA) | Artificial Analysis | – | 60.8% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 36.7% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 94.7% |
| MKA (AA) | Artificial Analysis | 54.6% | 43.9% |
| Maths | |||
| ProofBench | Vals AI | – | 91.0% |
| ArXivMath | MathArena | – | 58.3%† |
| BrokenArXiv | MathArena | – | 61.9%† |
| Arena Maths | Arena (LMArena) | – | 1485† |
| Knowledge | |||
| LiveBench 2.0 Data Analysis | LiveBench | 85.3%† | 79.1%† |
| LiveBench Research | LiveBench | 94.5%† | 82.1%† |
| AA-Omniscience v1.1 | Artificial Analysis | 53.8 | 29.9 |
| PRBench Finance | Scale AI SEAL | – | 47.5% |
| PRBench Legal | Scale AI SEAL | – | 47.9% |
| BioMysteryBench | Vals AI | – | 75.6%† |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 70.0%† |
| Access to Justice Benchmark | Vals AI | – | 69.5%† |
| DrugDiscoveryBench | Scale AI SEAL | – | 63.4%† |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 46.6%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 59.4% | 48.9% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 86.1% | 62.7% |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | 1522 | 1493† |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1519 | 1487† |
| EQ-Bench Creative Writing v3 | EQ-Bench | – | 2173 |
| Arena Creative Writing | Arena (LMArena) | 1514 | 1456† |
| Arena Multi-turn | Arena (LMArena) | 1529 | 1477† |
| Arena Longer Queries | Arena (LMArena) | 1521 | 1489† |
| Multimodal | |||
| LiveBench Design | LiveBench | 81.5%† | 73.7%† |
| MMMU-Pro | Artificial Analysis | – | 83.9% |
| Humanity's Sixth Sense | Scale AI SEAL | 75.9%† | 33.2%† |
| VIALS-AA | Handshake AI | – | 45.3% |
| AA-3D | Artificial Analysis | – | 1112 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | – | 86.3% |
| MLCR | Artificial Analysis | 28.9% | 38.3% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 161.4 |
| LiveBench 2.0 | LiveBench | 87.4%† | 68.7%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 59.6 | 46.5 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 55.1 |
| AA Progress Index v1 | Artificial Analysis | – | 340.7 |
| Vals Index | Vals AI | – | 62.5† |
| Vals Finance Index | Vals AI | – | 56.0%† |
| Vals Science Index | Vals AI | – | 44.4%† |
| Vals Legal Index | Vals AI | – | 67.0%† |
| AA Cyber Index | Artificial Analysis | – | 64.1 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 18.6% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 33.3 |
Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Kimi K3.1 Pro: BenchLeader Index 61.2 → 60.7.
- Gemini 4 Neon (high): 13 new results (MLCR, MKA (AA), Arena Text…).
- Gemini 4 Neon (high): first results.
- Kimi K3.1 Pro: BenchLeader Index 61.8 → 61.2.
- Kimi K3.1 Pro: 1 score revision.
- Kimi K3.1 Pro: BenchLeader Index 61.2 → 61.8.
- Kimi K3.1 Pro: 1 score revision.
- Kimi K3.1 Pro: 1 score revision.
- Kimi K3.1 Pro: 1 new result (HiL-Bench).
- Kimi K3.1 Pro: 3 new results (PRBench Finance, PRBench Legal, FORTRESS); 2 score revisions.
Related comparisons
- Gemini 4 Neon vs Claude Fable 5.2
- Gemini 4 Neon vs GPT-6.2 Astra
- Gemini 4 Neon vs Gemini 4 Carbon
- Kimi K3.1 Pro vs Claude Fable 5.2
- Kimi K3.1 Pro vs GPT-6.2 Astra
- Kimi K3.1 Pro vs Gemini 4 Carbon
- Kimi K3.1 Pro vs Claude Opus 5.5
- Gemini 4 Hydrogen vs Kimi K3.1 Pro
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 4 Neon vs Kimi K3.1 Pro: questions
- Is Gemini 4 Neon better than Kimi K3.1 Pro?
- Gemini 4 Neon (high) leads on quality: 67.3 vs 60.7. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Neon (high) is ahead overall as of 19 Nov 2026, but check the category scores for your use.
- Gemini 4 Neon vs Kimi K3.1 Pro: which is cheaper, and will that change?
- Kimi K3.1 Pro is cheaper today: $4.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Gemini 4 Neon or Kimi K3.1 Pro better for coding?
- Gemini 4 Neon scores higher in coding (73 vs 59 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 43.3% for Gemini 4 Neon against 25.4% for Kimi K3.1 Pro.
- Which is faster, Gemini 4 Neon or Kimi K3.1 Pro?
- Gemini 4 Neon streams 3×+ faster (101 vs 31 output tokens per second, Artificial Analysis 7-day median).
- Is Gemini 4 Neon or Kimi K3.1 Pro better for agents and tool use?
- Gemini 4 Neon scores higher in agentic tasks (76 vs 60 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Gemini 4 Neon answers first: 40.6 s against 155.6 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on Gemini 4 Neon vs Kimi K3.1 Pro?
- Across the 13 benchmarks both have, Gemini 4 Neon leads 10, Kimi K3.1 Pro leads 3. Every overall index that rates both puts Gemini 4 Neon ahead.
- When was Gemini 4 Neon released?
- Gemini 4 Neon was released on 18 Nov 2026.